Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    commas before sentences and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.64
    นาน
    1.52
    اد
    1.30
    𝗲
    1.30
    ्स
    1.29
    ний
    1.27
    $
    1.26
    大
    1.23
     ihe
    1.22
    ০
    1.22
    POSITIVE LOGITS
    鋈
    1.27
     Gabriella
    1.25
     médicas
    1.23
    garakan
    1.21
     Katherine
    1.20
     McGregor
    1.20
     generalizations
    1.18
     emociones
    1.18
     Carp
    1.14
     peripherals
    1.14
    Act Density 0.000%

    No Known Activations